Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Engineering Margins

ASecurity

Use when you must compute the margin of safety for a structural element and state it in an engineering report: compare the allowable load against the applied load, express the stress margin as a unitless decimal or a percent, and produce the pass/fail verdict on the limit basis or ultimate basis. Produces the margin of safety, the margin percent, the limit margin, and the one-line report sentence with consistent units in newtons. Trigger: margin of safety, engineering report, allowable load, ...

2 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspythonexpressdocumentation

Works with

claude code

Security Analysis

A100/100

Scanned 9/27/2026

Install to Claude Code

$npx -y skills add ashfordeOU/aero-agent-skills --skill engineering-margins --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Engineering Margins?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Engineering Margins
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-engineering-margins/badge)](https://www.skillsdirectory.com/skills/ashfordeou-engineering-margins)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: engineering-margins
description: "Use when you must compute the margin of safety for a structural element and state it in an engineering report: compare the allowable load against the applied load, express the stress margin as a unitless decimal or a percent, and produce the pass/fail verdict on the limit basis or ultimate basis. Produces the margin of safety, the margin percent, the limit margin, and the one-line report sentence with consistent units in newtons. Trigger: margin of safety, engineering report, allowable load, limit load, ultimate load, stress margin."
license: Apache-2.0
compliance: STANDARDS-REF
standards:
  - id: far-25
    reference-only: true
  - id: cs-25
    reference-only: true
gated: false
domain: cross-cutting
pack: cross-cutting
compatibility: "agentskills.io SKILL.md; any SKILL.md host (Claude Code, Hermes, OpenClaw)"
metadata:
  domain: cross-cutting
  subdomain: documentation
  tags: [margin-of-safety, engineering-report, allowable, limit-load, ultimate-load, documentation]
  version: 0.1.0
  author: Aero Agent Skills
---

# Engineering Margins (cross-cutting/documentation/engineering-margins)

Use when the task is the margin of safety for a structural element
and the report sentence that carries it: allowable versus applied
load, the limit basis and the ultimate basis, and the pass/fail
verdict. This is the cross-cutting documentation-pack discipline for
reporting margins; strength and allowable computation leaves live in
the structures pack.

## Domain quick reference

- Quantity convention: allowable and applied values are loads in
  newtons (N). Stresses in pascals (Pa) work identically because the
  margin is unitless, but a single call must never mix units: pick
  one unit (all N, or all Pa) and state it in the report. The
  Pa/MPa mix is the known bug class.
- Margin of safety MS = (allowable / applied) - 1, unitless decimal.
- MS >= 0 passes (allowable at least equals applied); MS < 0 fails.
- Margin percent = MS * 100, in percent.
- Limit margin ML = (limit_allowable / limit_applied) - 1, the limit
  basis check.
- Example: allowable 125000 N, applied 100000 N: MS = 0.25, pass.
- Example: allowable 90000 N, applied 100000 N: MS = -0.10, fail.

## Workflow

1. Pick the quantity and unit convention (loads in newtons), the
   same unit for both inputs.
2. Compute the margin with margin_of_safety.
3. Express it as a percent with margin_percent.
4. Check the limit basis with limit_margin.
5. Get the verdict with margin_verdict.
6. Write the report sentence with report_margin, naming the basis
   (limit or ultimate).

## Pitfalls

- Mixing units: Pa for one input and MPa for the other. The margin
  formula divides one value by the other, so mixed units silently
  corrupt the result. Pick one unit for both inputs.
- Reading a negative margin as an error: MS < 0 is a real fail
  verdict to report, not an exception.
- Forgetting the basis: the report sentence must state limit or
  ultimate.
- Reporting the percent margin as the decimal margin:
  margin_percent returns MS * 100, not MS.
- Writing the margin without the verdict: the report sentence
  carries the margin, the basis, and the pass/fail verdict.

## Behavior contract (gate 3)

The margin logic is exercised by the gate 3 contract test:
scripts/test_engineering_margins.py against
scripts/engineering_margins_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_engineering_margins.py

## Compliance

- Standards referenced, not reproduced: FAR-25 and CS-25 are
  referenced for the margin-of-safety practice; the margin formula
  is common structural-analysis methodology, summary-only per
  standards-map.yaml.
- compliance: STANDARDS-REF, gated: false.

Attribution

ashfordeOUashfordeOU
View sourceMore from ashfordeOU →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

694821 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →